Psychology, University of Johannesburg, Johannesburg, South Africa.
School of Chemistry of Physics, University of KwaZulu-Natal, Durban, South Africa.
Br J Soc Psychol. 2023 Jan;62(1):617-629. doi: 10.1111/bjso.12560. Epub 2022 Jul 23.
Word embeddings provide quantitative representations of word semantics and the associations between word meanings in text data, including in large repositories in media and social media archives. This article introduces social psychologists to word embedding research via a consideration of bias analysis, a topic of central concern in the discipline. We explain how word embeddings are constructed and how they can be used to measure bias along bipolar dimensions that are comparable to semantic differential scales. We review recent studies that show how familiar social biases can be detected in embeddings and how these change over time and in conjunction with real-world discriminatory practices. The evidence suggests that embeddings yield valid and reliable estimates of bias and that they can identify subtle biases that may not be communicated explicitly. We argue that word embedding research can extend scholarship on prejudice and stereotyping, providing measures of the bias environment of human thought and action.
词嵌入提供了文本数据中词语义和词之间关系的定量表示，包括媒体和社交媒体档案库中的大型存储库。本文通过对偏倚分析的考虑，向社会心理学家介绍了词嵌入研究，这是该学科关注的核心问题。我们解释了词嵌入是如何构建的，以及如何使用它们来衡量两极维度上的偏见，这些维度与语义差异量表相似。我们回顾了最近的研究，这些研究表明，熟悉的社会偏见可以在嵌入中被检测到，以及这些偏见如何随时间变化，并与现实世界中的歧视行为相结合。有证据表明，嵌入可以有效地和可靠地估计偏见，并且可以识别可能没有明确传达的微妙偏见。我们认为，词嵌入研究可以扩展关于偏见和刻板印象的学术研究，为人类思维和行为的偏见环境提供衡量标准。
